Chapter 25 sections from Deep Learning with PyTorch.
6 items
High-dimensional data often contains structure that can be described with fewer variables than the raw representation suggests.
An undercomplete autoencoder constrains the representation by reducing the latent dimension.
A denoising autoencoder learns to reconstruct a clean input from a corrupted version of that input. Instead of copying $x$ to $\hat{x}$, the model receives a noisy input $\tilde{x}$ and must recover the original $x$.
A variational autoencoder, or VAE, is an autoencoder with a probabilistic latent space.
A latent space is the internal coordinate system learned by an encoder or generative model.
Representation learning is the study of how a model converts raw data into useful internal variables.